vidore/arxivqa_test_subsampled_ocr_chunk
Viewer
•
Updated
•
1.44k
•
39
ViDoRe Chunk OCR (baseline)
The ViDoRe benchmark was passed to Unstructured to partition each page into text chunks. Detected figures/tables were captioned with Claude 3-Sonnet.
-
-
vidore/docvqa_test_subsampled_ocr_chunk
Viewer • Updated • 1.24k • 44 -
vidore/infovqa_test_subsampled_ocr_chunk
Viewer • Updated • 2.78k • 42 -
vidore/tabfquad_test_subsampled_ocr_chunk
Viewer • Updated • 636 • 33 -
vidore/tatdqa_test_ocr_chunk
Viewer • Updated • 8.54k • 55 -
vidore/shiftproject_test_ocr_chunk
Viewer • Updated • 2.05k • 37 -
vidore/syntheticDocQA_artificial_intelligence_test_ocr_chunk
Viewer • Updated • 1.9k • 82 -
vidore/syntheticDocQA_energy_test_ocr_chunk
Viewer • Updated • 2.29k • 68 -
vidore/syntheticDocQA_government_reports_test_ocr_chunk
Viewer • Updated • 1.9k • 60 -
vidore/syntheticDocQA_healthcare_industry_test_ocr_chunk
Viewer • Updated • 2.17k • 62